Intelligent Data Analysis - Volume 28, issue 5

Article Type: Editorial

DOI: 10.3233/IDA-249005

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1127-1129, 2024

Authors: Malhotra, Ruchika | Cherukuri, Madhukar

Article Type: Research Article

Abstract: BACKGROUND: Software quality prediction models play a crucial role in identifying vulnerable software components during early stages of development, and thereby optimizing the resource allocation and enhancing the overall software quality. While various classification algorithms have been employed for developing these prediction models, most studies have relied on default hyperparameter settings, leading to significant variability in model performance. Tuning the hyperparameters of classification algorithms can enhance the predictive capability of quality models by identifying optimal settings for improved accuracy and effectiveness. METHOD: This systematic review examines studies that have utilized hyperparameter tuning techniques to develop prediction …models in software quality domain. The review focused on diverse areas such as defect prediction, maintenance estimation, change impact prediction, reliability prediction, and effort estimation, as these domains demonstrate the wide applicability of common learning algorithms. RESULTS: This review identified 31 primary studies on hyperparameter tuning for software quality prediction models. The results demonstrate that tuning the parameters of classification algorithms enhances the performance of prediction models. Additionally, the study found that certain classification algorithms exhibit high sensitivity to their parameter settings, achieving optimal performance when tuned appropriately. Conversely, certain classification algorithms exhibit low sensitivity to their parameter settings, making tuning unnecessary in such instances. CONCLUSION: Based on the findings of this review, the study conclude that the predictive capability of software quality prediction models can be significantly improved by tuning their hyperparameters. To facilitate effective hyperparameter tuning, we provide practical guidelines derived from the insights obtained through this study. Show more

Keywords: Hyperparameter tuning, machine learning, defect prediction, effort estimation, maintenance prediction, reliability

DOI: 10.3233/IDA-230653

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1131-1149, 2024

Authors: Lin, Xinrui | Wang, Wei | Zhu, Xiaohui | Yue, Yong

Article Type: Research Article

Abstract: In the digital era, the rapid advancement of artificial intelligence has put a spotlight on target detection, especially in traffic settings. This area of study is pivotal for crucial projects like autonomous vehicles, road monitoring, and traffic sign recognition. However, existing Chinese traffic datasets lack comprehensive benchmarks for traffic signs and signals, and foreign datasets do not match Chinese traffic conditions. Manually annotating a large-scale dataset tailored for Chinese traffic conditions presents a significant challenge. This study addresses this gap by proposing a cross-augmentation method for image datasets. We utilized YOLOX for target detection and trained models on the BDD100K …dataset, achieving an impressive mAP of 60.25%, surpassing most algorithms. Leveraging transfer learning, we enhanced the CCTSDB dataset, creating the ACCTSDB dataset, which includes annotations for common traffic objects and Chinese traffic signs. Using YOLOX, we trained a traffic detector tailored for Chinese traffic scenarios, achieving an mAP of 75.79%. To further validate our approach, we conducted experiments on the TT100K dataset and successfully introduced the ATT100K dataset. Our methodology is poised to alleviate the limitations of manually annotating image datasets. The proposed ACCTSDB dataset and ATT100K dataset are expected to compensate for the lack of large-scale, multi-class traffic datasets in China. Show more

Keywords: Data augmentation, computer vision

DOI: 10.3233/IDA-230075

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1151-1169, 2024

Authors: Yu, Dongjin | Ni, Ke | Li, Zhongyang | Zhang, Shengyi | Sun, Xiaoxiao | Hou, Wenjie | Ying, Yuke

Article Type: Research Article

Abstract: Process discovery techniques analyze process logs to extract models that characterize the behavior of business processes. In real-life logs, however, noises exist and adversely affect the extraction and thus decrease the understandability of discovered models. In this paper, we propose a novel double granularity filtering method, executed on both the event and trace levels, to detect noises by analyzing the directly-following and parallel relations between events. Based on the probability of an event occurring in a sequence, the infrequent behaviors and redundant events in the logs can be filtered out. In addition, the missing events in parallel blocks are detected …to further improve the performance of filtering. Experiments on synthetic logs and five real-life datasets demonstrate that our method significantly outperforms other state-of-the-art methods. Show more

Keywords: Process discovery, process mining, event logs, noise filtering, event dependency, parallel relation

DOI: 10.3233/IDA-230118

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1171-1188, 2024

Authors: Shi, Xuefeng | Hu, Min | Ren, Fuji | Shi, Piao

Article Type: Research Article

Abstract: Active Learning (AL) is a technique being widely employed to minimize the time and labor costs in the task of annotating data. By querying and extracting the specific instances to train the model, the relevant task’s performance is improved maximally within limited iterations. However, rare work was conducted to fully fuse features from different hierarchies to enhance the effectiveness of active learning. Inspired by the thought of information compensation in many famous deep learning models (such as ResNet, etc.), this work proposes a novel TextCNN-based Two ways Active Learning model (TCTWAL) to extract task-relevant texts. TextCNN takes the advantage of …little hyper-parameter tuning and static vectors and achieves excellent results on various natural language processing (NLP) tasks, which are also beneficial to human-computer interaction (HCI) and the AL relevant tasks. In the process of the proposed AL model, the candidate texts are measured from both global and local features by the proposed AL framework TCTWAL depending on the modified TextCNN. Besides, the query strategy is strongly enhanced by maximum normalized log-probability (MNLP), which is sensitive to detecting the longer sentences. Additionally, the selected instances are characterized by general global information and abundant local features simultaneously. To validate the effectiveness of the proposed model, extensive experiments are conducted on three widely used text corpus, and the results are compared with with eight manual designed instance query strategies. The results show that our method outperforms the planned baselines in terms of accuracy, macro precision, macro recall, and macro F1 score. Especially, to the classification results on AG’s News corpus, the improvements of the four indicators after 39 iterations are 40.50%, 45.25%, 48.91%, and 45.25%, respectively. Show more

Keywords: Active learning, TextCNN, maximum normalized log-probability, global information, local feature

DOI: 10.3233/IDA-230332

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1189-1211, 2024

Authors: Zhang, Ji | Yu, Mingxin | Lu, Wenshuai | Dai, Yuxiang | Shi, Huiyu | You, Rui

Article Type: Research Article

Abstract: Transformer-based networks have revolutionized visual tasks with their continuous innovation, leading to significant progress. However, the widespread adoption of Vision Transformers (ViT) is limited due to their high computational and parameter requirements, making them less feasible for resource-constrained mobile and edge computing devices. Moreover, existing lightweight ViTs exhibit limitations in capturing different granular features, extracting local features efficiently, and incorporating the inductive bias inherent in convolutional neural networks. These limitations somewhat impact the overall performance. To address these limitations, we propose an efficient ViT called Dual-Granularity Former (DGFormer). DGFormer mitigates these limitations by introducing two innovative modules: Dual-Granularity Attention (DG …Attention) and Efficient Feed-Forward Network (Efficient FFN). In our experiments, on the image recognition task of ImageNet, DGFormer surpasses lightweight models such as PVTv2-B0 and Swin Transformer by 2.3% in terms of Top1 accuracy. On the object detection task of COCO, under RetinaNet detection framework, DGFormer outperforms PVTv2-B0 and Swin Transformer with increase of 0.5% and 2.4% in average precision (AP), respectively. Similarly, under Mask R-CNN detection framework, DGFormer exhibits improvement of 0.4% and 1.8% in AP compared to PVTv2-B0 and Swin Transformer, respectively. On the semantic segmentation task on the ADE20K, DGFormer achieves a substantial improvement of 2.0% and 2.5% in mean Intersection over Union (mIoU) over PVTv2-B0 and Swin Transformer, respectively. The code is open-source and available at: https://github.com/ISCLab-Bistu/DGFormer.git . Show more

Keywords: Transformer, object detection, classification, semantic segmentation

DOI: 10.3233/IDA-230799

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1213-1228, 2024

Authors: Hu, Haiping | Huo, Wei | Yan, Yingying | Zhu, Qiuyu

Article Type: Research Article

Abstract: For the pattern recognition, most classification models are solved iteratively, except for Linear LDA, KLDA and ELM etc. In this paper, a nonlinear classification network model based on predefined evenly-distributed class centroids (PEDCC) is proposed. Its analytical solution can be obtained and has good interpretability. Using the characteristics of maximizing the inter-class distance of PEDCC and derivative weighted minimum mean square error loss function to minimize the intra-class distance, we can not only realize the effective nonlinearity of the network, but also obtain the analytical solution of the network weight. Then, the sample is classified based on GDA. In order …to further improve the performance of classification, PCA is used to reduces the dimensionality of the original sample, meanwhile, the CReLU activation function are adopted to enhances the expression ability of the features. The network transforms the samples into the higher dimensional feature space through the weighted minimum mean square error, so as to find a better separation hyperplane. In experiments, the feasibility of the network structure is verified from pure linear 𝑾 , 𝑾 + Tanh, and PCA+ 𝑾 + Tanh respectively on many small data sets and large data sets, and compared with SVM and ELM in terms of training speed and recognition rate. The results show that, in general, this model has advantages on small data set both in recognition accuracy and training speed, while it has advantages in training speed on large data sets. Finally, by introducing a multi-stage network structure based on the latent feature norm, the classifier network can further significantly improve the classification performance, the recognition rate of small data sets is effectively improved and much higher than that of existing methods, while the recognition rate of large data sets is similar to that of SVM. Show more

Keywords: Pattern recognition, image classification, machine learning, GDA

DOI: 10.3233/IDA-230044

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1229-1244, 2024

Authors: Zhou, Rucheng | Zhang, Dongmei | Zhu, Jiabao | Min, Geyong

Article Type: Research Article

Abstract: Traffic forecasting has become a core component of Intelligent Transportation Systems. However, accurate traffic forecasting is very challenging, caused by the complex traffic road networks. Most existing forecasting methods do not fully consider the topological structure information of road networks, making it difficult to extract accurate spatial features. In addition, spatial and temporal features have different impacts on traffic conditions, but the existing studies ignore the distribution of spatial-temporal features in traffic regions. To address these limitations, we propose a novel graph neural network architecture named Attention-based Spatial-Temporal Adaptive Integration Gated Network (AST-AIGN). The originality of AST-AIGN is to obtain …a spatial feature that more accurately reflects the topological structure of the road networks by embedding Graph Attention Network (GAT) into Jumping Knowledge Net (JK-Net). We propose a data-dependent function called spatial-temporal adaptive integration gate to process the diversity of feature distribution and highlight features in road networks that significantly affects traffic conditions. We evaluate our model on two real-world traffic datasets from the Caltrans Performance Measurement System (PEMS04 and PEMS08), and the extensive experimental results demonstrate the proposed AST-AIGN architecture outperforms other baselines. Show more

Keywords: Traffic forecasting, spatial-temporal dependences, jumping knowledge, gating mechanism, self-attention

DOI: 10.3233/IDA-230101

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1245-1269, 2024

Authors: Zhang, Shuo | Hu, Xingbang | Zhang, Wenbo | Chen, Jinyi | Huang, Hejiao

Article Type: Research Article

Abstract: For modern Intelligent Transportation System (ITS), data missing during traffic raster acquisition can be inevitable because of the loop detector malfunction or signal interference. Nevertheless, missing data imputation is meaningful due to the periodic spatio-temporal characteristics and individual randomness of traffic raster data. In this paper, traffic raster data collected from all spatial regions at each time interval are considered as a multiple channel image. Accordingly, the traffic raster data over a period of time can be regarded as video, on which an unsupervised generative neural network called MSST-VAE (Multiple Streams Spatial Temporal-VAE) is proposed for traffic raster data imputation, …and this model can even robustly performs at varied missing rates while many other approaches fail to conduct. Two major innovations can be summarized in MSSTVAE: Firstly, it uses multiple periodic streams of Variational Auto-Encoders (VAEs) with Sylvester Normalizing Flows (SNFs), which shows strong generalization ability. Secondly, after the traffic raster data are transferred into videos, an ECB (Extraction-and-Calibration Block) consisting of dilated P3D gated convolution and multi-horizon attention mechanism is employed to learn global-local-granularity spatial features and long-short-term temporal features. Extensive experiments on three real traffic flow datasets validate that MSST-VAE outperforms other classical traffic imputation models with the least imputation error. Show more

Keywords: Intelligent transportation system, traffic raster data, data imputation

DOI: 10.3233/IDA-230091

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1271-1292, 2024

Authors: Zhong, Qing | Shao, Xinhui

Article Type: Research Article

Abstract: For the aspect-based sentiment analysis task, traditional works are only for text modality. However, in social media scenarios, texts often contain abbreviations, clerical errors, or grammatical errors, which invalidate traditional methods. In this study, the cross-model hierarchical interactive fusion network incorporating an end-to-end approach is proposed to address this challenge. In the network, a feature attention module and a feature fusion module are proposed to obtain the multimodal interaction feature between the image modality and the text modality. Through the attention mechanism and gated fusion mechanism, these two modules realize the auxiliary function of image in the text-based aspect-based sentiment …analysis task. Meanwhile, a boundary auxiliary module is used to explore the dependencies between two core subtasks of the aspect-based sentiment analysis. Experimental results on two publicly available multi-modal aspect-based sentiment datasets validate the effectiveness of the proposed approach. Show more

Keywords: Multimodal aspect-based sentiment analysis, hierarchical interactive fusion, multi-head interaction attention mechanism, gated mechanism

DOI: 10.3233/IDA-230305

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1293-1308, 2024

Authors: Nayancy, | Dutta, Sandip | Chakraborty, Soubhik

Article Type: Research Article

Abstract: Blockchain has attracted tremendous attention in recent years due to its significant features including anonymity, security, immutability, and audibility. Blockchain technology has been used in several nonmonetary applications, including Internet-of-Things. Though blockchain has limited resources, and scalability is computationally expensive, resulting in delays and large bandwidth overhead that are unsuitable for many IoT devices. In this paper, we work on a lightweight blockchain approach that is suited for IoT needs and provides end-to-end security. Decentralization is achieved in our lightweight blockchain implementation by building a network with a lot of high-resource devices collaborate to maintain the blockchain. The nodes in …the network is arranged in sorted order w.r.t execution time and count to reduce the mining overheads and is accountable for handling the public blockchain. We propose a distributed execution time-based consensus algorithm that decreases the delay and overhead of the mining process. We also propose a randomized node-selection algorithm for the selection of nodes to verify the mined blocks to eliminate the double-spend and 51% attack. The results are encouraging and significantly reduce the mining overhead and keep a check on the double-spending problem and 51% attack. Show more

Keywords: Blockchain, IoT, lightweight consensus, double-spend attack, 51% attack

DOI: 10.3233/IDA-230153

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1309-1319, 2024

Authors: Al-Jumaili, Ahmed Hadi Ali | Muniyandi, Ravie Chandren | Hasan, Mohammad Kamrul | Singh, Mandeep Jit | Paw, Johnny Koh Siaw | Al-Jumaily, Abdulmajeed

Article Type: Research Article

Abstract: Parallel power loads anomalies are processed by a fast-density peak clustering technique that capitalizes on the hybrid strengths of Canopy and K-means algorithms all within Apache Mahout’s distributed machine-learning environment. The study taps into Apache Hadoop’s robust tools for data storage and processing, including HDFS and MapReduce, to effectively manage and analyze big data challenges. The preprocessing phase utilizes Canopy clustering to expedite the initial partitioning of data points, which are subsequently refined by K-means to enhance clustering performance. Experimental results confirm that incorporating the Canopy as an initial step markedly reduces the computational effort to process the vast quantity …of parallel power load abnormalities. The Canopy clustering approach, enabled by distributed machine learning through Apache Mahout, is utilized as a preprocessing step within the K-means clustering technique. The hybrid algorithm was implemented to minimise the length of time needed to address the massive scale of the detected parallel power load abnormalities. Data vectors are generated based on the time needed, sequential and parallel candidate feature data are obtained, and the data rate is combined. After classifying the time set using the canopy with the K-means algorithm and the vector representation weighted by factors, the clustering impact is assessed using purity, precision, recall, and F value. The results showed that using canopy as a preprocessing step cut the time it proceeds to deal with the significant number of power load abnormalities found in parallel using a fast density peak dataset and the time it proceeds for the k-means algorithm to run. Additionally, tests demonstrate that combining canopy and the K-means algorithm to analyze data performs consistently and dependably on the Hadoop platform and has a clustering result that offers a scalable and effective solution for power system monitoring. Show more

Keywords: Power load data, abnormality detection and adjustment, hybrid (CKMA), K-means algorithm (KMA), canopy algorithm (CA), Apache Mahout

DOI: 10.3233/IDA-230573

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1321-1346, 2024

Authors: Boullé, Marc

Article Type: Research Article

Abstract: Histograms are among the most popular methods used in exploratory analysis to summarize univariate distributions. In particular, irregular histograms are good non-parametric density estimators that require very few parameters: the number of bins with their lengths and frequencies. Although many approaches have been proposed in the literature to infer these parameters, most existing histogram methods are difficult to exploit for exploratory analysis in the case of real-world data sets, with scalability issues, truncated data, outliers or heavy-tailed distributions. In this paper, we focus on the G-Enum histogram method, which exploits the Minimum Description Length (MDL) principle to build histograms without …any user parameter. We then propose to extend this method by exploiting a new modeling space based on floating-point representation, with the objective of building histograms resistant to outliers or heavy-tailed distributions. We also suggest several heuristics and a methodology suitable for the exploratory analysis of large scale real-world data sets, whose underlying patterns are difficult to recover for digitization reasons. Extensive experiments show the benefits of the approach, evaluated with a dual objective: the accuracy of density estimation in the case of outliers or heavy-tailed distributions, and the effectiveness of the approach for exploratory data analysis. Show more

Keywords: Density estimation, histograms, model selection, minimum description length, exploratory analysis

DOI: 10.3233/IDA-230638

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1347-1394, 2024

Authors: K, Subha | N, Bharathi

Article Type: Research Article

Abstract: In today’s digital era, the generation and sharing of information are rapidly expanding. The increased volume of complex data is big data. YouTube is the primary source of big data. The proliferation of the internet and smart devices has led to a significant increase in content creators on social media platforms, with YouTube being a prominent example. There has been a substantial increase in content creators across various social media platforms, with YouTube emerging as one of the foremost platforms for content generation and sharing. YouTubers face challenges in enhancing content strategies due to the growing number of comments, such …as big data on shared videos. Reading and finding viewers’ opinions of such a large amount of data through manual methods is time-consuming and challenging and makes it hard to understand people’s sentiments. To address this, spark-based machine learning algorithms have emerged as a transformative tool for content creators to understand the audience. The Improved Novel Ensemble Method (INEM) algorithm is designed to predict viewers’ sentiments and emotional responses based on the content they interact through the comments. The proposed results provide valuable insights for content creators, helping them refine the strategies to optimize the channel’s revenue and performance. Fit Tuber Channel is analyzed to perform the sentiment of user comments. Show more

Keywords: Big data, sentiment analysis, machine learning, social-media, spark

DOI: 10.3233/IDA-240198

Citation: Intelligent Data Analysis, vol. 28, no. 5, pp. 1395-1405, 2024